Date: Thu, 20 Jan 2005 14:11:29 -0500
Reply-To: Richard Ristow <firstname.lastname@example.org>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Richard Ristow <email@example.com>
Subject: Re: How to graph outliers etc.
Content-Type: text/plain; charset="us-ascii"; format=flowed
Repeating, with a little more information (my machine's feeling
At 07:25 PM 1/19/2005, Martha Moore wrote:
>Let's say I have data like this:
>Public School/ Private School/School size/ then Books read per
>year Cost of attending
>Code for Public/Private and School size categories. numbers for books
>read and cost etc. How can I plot or graph this to show central
>tendencies and outliers?
>>Very quickly: try command "Examine", from the "Analyze" menu.
Specifically, Analyze/Descriptive Statistics/Explore.
WATCH OUT! The syntax command is "Examine"; the menu entry is
This is syntax I clicked up and recovered from the SPSS journal
(remember the journal?):
VARIABLES=hv_rtn BY mob_educ /ID= mom_unq
A. In "Plots", I un-checked "Stem-and-leaf" under "Descriptive"; it's
checked by default. (It produces a printer-graphics plot that I don't
find useful; but stem-and-leaf plots are well thought of in by some
B. Subcommand "/STATISTICS DESCRIPTIVES" gives a long table of
statistics for each category; it may be 'more than you want to know'.
The second statistical column, where given, is the standard error of
estimate. I've edited it; it's a lot more compact than the original:
Mean |12.8533 |.5675 |
5% Trimmed Mean |11.9797 | |
Median |5.7167 | |
Variance |203.567 | |
Std. Deviation |14.2677 | |
Minimum |.00 | |
Maximum |42.60 | |
Range |42.60 | |
Interquartile Range |20.2583 | |
Skewness |.956 |.097 |
Kurtosis |-.643 |.194 |